Naming, Describing, and Quantifying Visual Objects in Humans and LLMs

Alberto Testoni, Juell Sprott, Sandro Pezzelle


Abstract
While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision & Language Large Language Models (VLLMs) can mimic this crucial feature of language use is an open question. This applies to common, everyday objects, but it is particularly interesting for uncommon or novel objects for which a category label may be lacking or fuzzy. Furthermore, similar patterns of variation are observed among human speakers for highly context-sensitive expressions, such as the quantifiers ‘few’ or ‘most’. In our work, we evaluate VLLMs (FROMAGe, BLIP-2, LLaVA) on three categories (nouns, attributes, and quantifiers) where humans show great subjective variability concerning the distribution over plausible labels, using datasets and resources mostly under-explored in previous work. Our results reveal mixed evidence on the ability of VLLMs to capture human naming preferences at generation time: while some models are good at mimicking human distributions for nouns and attributes, all of them fail to assign quantifiers, a task that requires more accurate, high-level reasoning.
Anthology ID:
2024.acl-short.50
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
547–557
Language:
URL:
https://aclanthology.org/2024.acl-short.50
DOI:
10.18653/v1/2024.acl-short.50
Bibkey:
Cite (ACL):
Alberto Testoni, Juell Sprott, and Sandro Pezzelle. 2024. Naming, Describing, and Quantifying Visual Objects in Humans and LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 547–557, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Naming, Describing, and Quantifying Visual Objects in Humans and LLMs (Testoni et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.acl-short.50.pdf